CtrlK
BlogDocsLog inGet started
Tessl Logo

paper-slides

Generate conference presentation slides (beamer LaTeX → PDF + editable PPTX) from a compiled paper, with speaker notes and full talk script. Use when user says "做PPT", "做幻灯片", "make slides", "conference talk", "presentation slides", "生成slides", "写演讲稿", or wants beamer slides for a conference talk.

63

Quality

77%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Critical

Do not install without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/paper-slides/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an excellent skill description that clearly specifies concrete outputs (beamer LaTeX PDF, PPTX, speaker notes, talk script), the input context (compiled paper for conference), and provides comprehensive bilingual trigger terms. It is well-scoped to a distinct niche and follows all best practices including third-person voice and explicit 'Use when' guidance.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: generate conference presentation slides, produce beamer LaTeX → PDF + editable PPTX, create speaker notes and full talk script, all from a compiled paper.

3 / 3

Completeness

Clearly answers both 'what' (generate conference presentation slides with beamer LaTeX → PDF + PPTX, speaker notes, talk script from a compiled paper) and 'when' (explicit 'Use when' clause with specific trigger phrases).

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms in both English and Chinese: '做PPT', '做幻灯片', 'make slides', 'conference talk', 'presentation slides', '生成slides', '写演讲稿', 'beamer slides'. These are terms users would naturally say.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive niche: specifically targets conference presentations from compiled academic papers using beamer LaTeX, which is clearly different from general presentation skills or general LaTeX skills. The academic conference context and beamer specification make it unlikely to conflict with other skills.

3 / 3

Total

12

/

12

Passed

Implementation

55%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is extremely thorough and actionable with an excellent multi-phase workflow, explicit checkpoints, and error recovery. However, it is massively over-engineered for a SKILL.md — at 500+ lines it wastes significant context window space by inlining complete templates, exhaustive tables, and detailed examples that Claude could generate from concise instructions. The lack of bundle files means all content is crammed into a single monolithic document that would benefit enormously from splitting into supporting reference files.

Suggestions

Extract the full LaTeX beamer template, talk script template, and PPTX generation script into separate bundle files (e.g., templates/beamer_template.tex, templates/talk_script_template.md, scripts/generate_pptx.py) and reference them from the SKILL.md.

Remove the venue color scheme table and talk-type slide breakdown tables — condense to a brief description and put detailed tables in a reference file like SLIDE_FORMATS.md.

Remove explanations Claude already knows: what makes a good talk, how beamer works, what progressive disclosure means in presentations, the full Q&A template with 8 example questions.

Trim the style-ref section significantly — the 30-line bash resolution script and detailed error handling could be in a helper script file rather than inlined in the SKILL.md body.

DimensionReasoningScore

Conciseness

Extremely verbose at ~500+ lines. Includes extensive tables, templates, and examples that Claude could generate from brief instructions. The venue color scheme table, full LaTeX template, full talk script template with Q&A examples, and detailed slide-by-slide breakdowns for every talk type are all excessive. Much of this (e.g., what makes a good talk, beamer syntax, python-pptx usage) is knowledge Claude already has.

1 / 3

Actionability

Highly actionable with executable bash commands, complete LaTeX templates, specific python-pptx generation steps, concrete formatting rules (max 6 lines, 8 words/line), and copy-paste ready code blocks throughout. Every phase has concrete, executable guidance.

3 / 3

Workflow Clarity

Excellent 9-phase workflow (Phase 0-8) with clear sequencing, explicit checkpoints (especially the critical Phase 1 outline checkpoint with stop-and-wait), error handling loops (Phase 4 max 3 attempts), state persistence via SLIDES_STATE.json for recovery, and validation steps like PDF page count verification.

3 / 3

Progressive Disclosure

Monolithic wall of text with no bundle files to offload content to. The full LaTeX template, full talk script template, complete Q&A section, all venue color schemes, all talk-type slide breakdowns, and the style-ref helper script are all inlined. References to external files (SLIDE_OUTLINE.md, SLIDES_REVIEW.md) are outputs, not supporting references. The recommended follow-up section adds more bulk without being actionable within this skill.

1 / 3

Total

8

/

12

Passed

Validation

72%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation8 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (632 lines); consider splitting into references/ and linking

Warning

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

8

/

11

Passed

Repository
wanshuiyin/Auto-claude-code-research-in-sleep
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.